An elastic wave filter generation method, device, apparatus, and storage medium

Abstract

An elastic wave filter generation method, device, equipment and storage medium are disclosed. The method comprises: obtaining a target parameter; inputting the target parameter into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structure parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model based on a first sample set; determining a first parameter corresponding to an initial response curve of the elastic wave filter based on the initial elastic wave filter topology structure and the initial structure parameters of each resonator in the elastic wave filter; and determining a target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology structure and the initial structure parameters of each resonator in the elastic wave filter. The method realizes automatic, rapid and accurate simulation design of the elastic wave filter, and reduces the experience requirement for the designer.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of filter simulation technology, and in particular to a method, apparatus, device and storage medium for generating elastic wave filters. Background Technology

[0002] Since the advent of the LTE era, elastic wave filters have played an increasingly important role in communication systems. Simultaneously, with the development of communication technology, the requirements for filters are becoming increasingly stringent; especially with the arrival of 5G, the filter industry faces both significant challenges and opportunities.

[0003] Elastic wave filters are widely used in RF front-ends, offering advantages such as low insertion loss, wide bandwidth, and small size. However, designing elastic wave filters has always been a challenge. Currently, there are two main methods for elastic wave filter design: phenomenological modeling and precise simulation. Phenomenological modeling uses equivalent circuits or coupled-mode methods to map the structural parameters of the elastic wave resonator to its electrical curves based on its main electrical curve characteristics. However, this method has some drawbacks, such as the inability to simulate transverse modes, predict higher-order modes, and account for multi-mode coupling clutter, which limits its application in the design of high-performance elastic wave filters like TCSAW / TFSAW. Precise simulation uses finite element method (FEM) or finite element-boundary element method (FEBEM) to simulate the elastic wave resonator through multi-physics coupling, thereby obtaining its electrical curves. However, this method is slow and requires significant computational resources. Although computer performance has improved significantly in recent years, and HCT acceleration schemes have improved the simulation speed of precise simulation to some extent, this approach is still relatively slow, especially for forward design, and cannot meet the rapid design needs of companies. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for generating elastic wave filters, which enables automatic, fast, and accurate simulation design of elastic wave filters while reducing the experience requirements for designers.

[0005] In a first aspect, embodiments of the present invention provide a method for generating an elastic wave filter, comprising:

[0006] Obtain the target parameters;

[0007] The target parameters are input into the filter topology algorithm model to obtain the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. The filter topology algorithm model is obtained by iteratively training a first model using a first sample set.

[0008] The first parameter corresponding to the initial response curve of the elastic wave filter is determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter.

[0009] The target elastic wave filter layout is determined based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

[0010] Optionally, the first parameter corresponding to the initial response curve of the elastic wave filter is determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, including:

[0011] The initial elastic wave filter layout and the corresponding electromagnetic response curve are determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter.

[0012] The initial structural parameters of each resonator in the elastic wave filter are sequentially input into the resonator algorithm model to obtain the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter. The resonator algorithm model is obtained by iteratively training a second model using a second sample set.

[0013] The initial response curve of the elastic wave filter is obtained by cascading the response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the initial elastic wave filter layout.

[0014] The first parameter corresponding to the initial response curve of the elastic wave filter is determined based on the initial response curve of the elastic wave filter.

[0015] Optionally, the target elastic wave filter layout is determined based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter, including:

[0016] If the difference between the first parameter and the target parameter is less than or equal to the difference threshold, then the initial elastic wave filter layout determined according to the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter will be determined as the target elastic wave filter layout.

[0017] Optional, also includes:

[0018] If the difference between the first parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonator in the elastic wave filter are adjusted according to the first parameter and the target parameter.

[0019] The second parameter corresponding to the first response curve of the elastic wave filter is determined based on the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout.

[0020] If the difference between the second parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonators in the elastic wave filter are adjusted according to the second parameter and the target parameter. Based on the adjusted structural parameters of the resonators, the operation of determining the second parameter corresponding to the first response curve of the elastic wave filter according to the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout is performed until the difference between the second parameter and the target parameter is less than or equal to the difference threshold, thus obtaining the target structural parameters of each resonator in the elastic wave filter.

[0021] The first elastic wave filter layout and the corresponding electromagnetic response curve of the first elastic wave filter layout are determined based on the initial elastic wave filter topology and the target structural parameters of each resonator in the elastic wave filter.

[0022] The third parameter corresponding to the second response curve of the elastic wave filter is determined based on the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout.

[0023] If the difference between the third parameter and the target parameter is less than or equal to the difference threshold, then the first elastic wave filter layout is determined as the target elastic wave filter layout.

[0024] Optional, also includes:

[0025] If the difference between the third parameter and the target parameter is greater than the difference threshold, the initial elastic wave filter topology is adjusted according to the third parameter and the target parameter.

[0026] Based on the adjusted elastic wave filter topology, the operation of determining the first elastic wave filter layout and the corresponding electromagnetic response curve of the first elastic wave filter layout according to the target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology is performed. The operation of determining the third parameter corresponding to the second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout is performed until the difference between the third parameter and the target parameter is less than or equal to the difference threshold, thus obtaining the target elastic wave filter topology.

[0027] The layout of the target elastic wave filter is determined based on the target elastic wave filter topology and the target structural parameters of the resonators in the elastic wave filter.

[0028] Optionally, the first model is trained iteratively using the first sample set, including:

[0029] Obtain a filter topology database and a filter knowledge graph;

[0030] A first sample set is generated based on the filter topology database and the filter knowledge graph. The first sample set includes: parameter samples, filter topology structures corresponding to the parameter samples, and structural parameters of each resonator in the filter corresponding to the parameter samples.

[0031] The filter topology algorithm model is obtained by iteratively training the first model using the first sample set.

[0032] Optionally, a second model may be trained iteratively using a second sample set, including:

[0033] Obtain the database of elastic wave resonators;

[0034] A second sample set is created based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of elastic wave resonators;

[0035] The second model is trained using the second sample set to obtain the elastic wave resonator algorithm model.

[0036] Optionally, the target parameters include: insertion loss, out-of-band rejection, center frequency, input VSWR, output VSWR, input impedance, and output impedance.

[0037] Secondly, embodiments of the present invention provide an elastic wave filter generation device, comprising:

[0038] The acquisition module is used to acquire target parameters;

[0039] The input module is used to input the target parameters into the filter topology algorithm model to obtain the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model with a first sample set;

[0040] The first determining module is used to determine the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter.

[0041] The second determining module is used to determine the target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

[0042] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising:

[0043] At least one processor; and

[0044] A memory communicatively connected to the at least one processor; wherein,

[0045] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the elastic wave filter generation method according to any embodiment of the present invention.

[0046] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the elastic wave filter generation method described in any embodiment of the present invention.

[0047] This invention addresses the problem of slow simulation and design of elastic wave filters in existing technologies by acquiring target parameters; inputting the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model using a first sample set; determining the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter; and determining the target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameters, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter. This achieves automatic, fast, and accurate simulation design of elastic wave filters while reducing the experience requirements for designers.

[0048] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart of an elastic wave filter generation method provided in Embodiment 1 of the present invention;

[0051] Figure 2 This is a target parameter table diagram provided in Embodiment 1 of the present invention;

[0052] Figure 3 This is a flowchart of an elastic wave filter generation method provided in Embodiment 2 of the present invention;

[0053] Figure 4 This is a comparison chart of the prediction results of a resonator algorithm model provided in Embodiment 2 of the present invention;

[0054] Figure 5 This is a flowchart illustrating a method for generating an elastic wave filter according to Embodiment 2 of the present invention.

[0055] Figure 6 This is a schematic diagram of the structure of an elastic wave filter generation device provided in Embodiment 3 of the present invention;

[0056] Figure 7 This is a schematic diagram of the structure of an electronic device that can be used to implement embodiments of the present invention. Detailed Implementation

[0057] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0058] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0059] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0060] Example 1

[0061] Figure 1 This is a flowchart of an elastic wave filter generation method provided in Embodiment 1 of the present invention. This embodiment is applicable to the design and generation of elastic wave filters. The method can be executed by the elastic wave filter generation device in this embodiment, which can be implemented in software and / or hardware, such as... Figure 1 As shown, the method specifically includes the following steps:

[0062] S110, obtain the target parameters.

[0063] The target parameters can refer to pre-defined target parameters, such as insertion loss, out-of-band rejection, center frequency, VSWR, impedance, etc.; specifically, they can be obtained from a target parameter table provided by the customer.

[0064] In this embodiment, the target parameters can be obtained directly from the target parameter table provided in advance by the customer.

[0065] S120, the target parameters are input into the filter topology algorithm model to obtain the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training the first model with the first sample set.

[0066] The filter topology algorithm model enables automatic filter design. The initial elastic wave filter topology refers to the connection configuration of each resonator in the elastic wave filter. The filter contains multiple resonators, and the initial structural parameters differ for each resonator. For example, if the resonator is a surface acoustic wave (SAW) resonator, the initial structural parameters may include: interpolation period, number of interpolation fingers, duty cycle, resonator metal thickness, and resonator aperture. If the resonator is a bulk acoustic wave (BAW) resonator, the initial structural parameters may include: resonator area, piezoelectric layer thickness, electrode thickness, and frequency modulation layer thickness. The first sample set refers to the sample set used to train the first model to obtain the filter topology algorithm model; the first model may refer to the algorithm model of an artificial neural network.

[0067] In this embodiment, the filter topology algorithm model is obtained by iteratively training the algorithm model of the artificial neural network through the first sample set. By inputting the pre-acquired target parameters into the filter topology algorithm model, the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter can be obtained.

[0068] S130, determine the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter.

[0069] Specifically, the initial response curve can be determined as follows: Based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, determine the initial elastic wave filter layout. Simulate the initial elastic wave filter layout using an electromagnetic FEM module to obtain the electromagnetic response curve corresponding to the initial elastic wave filter layout. Then, cascade the response curves corresponding to the initial structural parameters of each resonator and the electromagnetic response curves corresponding to the initial elastic wave filter layout to obtain the initial response curve of the elastic wave filter.

[0070] The first parameter can refer to the parameter corresponding to the target parameter, such as insertion loss, out-of-band rejection, center frequency, VSWR, impedance, etc.

[0071] In this embodiment, the initial response curve of the elastic wave filter can be determined by the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. Then, the first parameter corresponding to the initial response curve of the elastic wave filter can be determined based on the initial response curve of the elastic wave filter.

[0072] S140, determine the target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

[0073] The elastic wave filter layout can refer to the resonators in the elastic wave filter, the connections between the resonators, and the attribute values ​​of each resonator, such as resonant frequency and anti-resonant frequency. The target elastic wave filter layout can refer to the latest elastic wave filter layout.

[0074] Specifically, the difference between the first parameter and the target parameter corresponding to the initial response curve of the elastic wave filter can be used to determine whether the initial response curve meets the target specifications. If it does, the initial elastic wave filter layout determined by the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter can be used as the latest elastic wave filter layout. If it does not meet the requirements, the latest elastic wave filter layout can be determined by adjusting the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter.

[0075] In this embodiment, the latest elastic wave filter layout can be determined by the difference between the first parameter and the target parameter corresponding to the initial response curve of the elastic wave filter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter. The layout can be automatically generated and optimized according to the target specifications. The manual operation is only to click the response button, which improves the design efficiency and reduces the experience requirements of the designers.

[0076] The technical solution of this embodiment obtains target parameters; inputs the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model using a first sample set; determines the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter; and determines the target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameters, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter. This solves the problem of slow simulation and design of elastic wave filters in the prior art, realizes automatic, fast, and accurate simulation design of elastic wave filters, and reduces the experience requirements for designers.

[0077] Optionally, the target parameters include: insertion loss, out-of-band rejection, center frequency, input VSWR, output VSWR, input impedance, and output impedance.

[0078] Specifically, Figure 2 This is a target parameter table diagram provided in Embodiment 1 of the present invention, such as... Figure 2As shown, the target parameters include: insertion loss, out-of-band rejection, center frequency, in-band ripple (the ripple value of insertion loss), input VSWR (the closer to 1 the better, the larger the worse, generally required to be below 2), output VSWR (the closer to 1 the better, the larger the worse, generally required to be below 2), input impedance, and output impedance.

[0079] In this embodiment, the target parameters can be directly obtained from the target parameter chart. The target parameters include: insertion loss, out-of-band rejection, center frequency, input VSWR, output VSWR, input impedance, and output impedance. The initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter can be obtained quickly, thereby quickly obtaining the initial response curve of the elastic wave filter, avoiding the large amount of time required for accurate simulation, and improving the design and generation efficiency of the elastic wave filter.

[0080] Example 2

[0081] Figure 3 This is a flowchart of an elastic wave filter generation method provided in Embodiment 2 of the present invention. The technical solution of this embodiment is further refined based on the above embodiments. Figure 3 As shown, the method includes:

[0082] S210, obtain the target parameters.

[0083] S220, the target parameters are input into the filter topology algorithm model to obtain the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training the first model with the first sample set.

[0084] S230, Determine the initial elastic wave filter layout and the corresponding electromagnetic response curve of the initial elastic wave filter layout based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter;

[0085] Specifically, the initial elastic wave filter layout can be determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. After determining the initial elastic wave filter layout, the electromagnetic response curve corresponding to the initial elastic wave filter layout can be obtained by simulating the initial elastic wave filter layout.

[0086] S240, the initial structural parameters of each resonator in the elastic wave filter are sequentially input into the resonator algorithm model to obtain the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter. The resonator algorithm model is obtained by iteratively training the second model using the second sample set.

[0087] In this context, each resonator in the elastic wave filter has a corresponding response curve. Specifically, the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter can be determined through the resonator algorithm model. The second sample set can refer to the sample set used to train the second model to obtain the resonator algorithm model. The second model can refer to the algorithm model of an artificial neural network.

[0088] In this embodiment, by sequentially inputting the initial structural parameters of each resonator in the elastic wave filter into a pre-trained resonator algorithm model, the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter is obtained.

[0089] S250, the response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the initial elastic wave filter layout are cascaded to obtain the initial response curve of the elastic wave filter.

[0090] In this embodiment, the initial response curve of the elastic wave filter can be obtained by cascading the response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter determined by the resonator algorithm model and the electromagnetic response curves corresponding to the initial elastic wave filter layout obtained by simulating the initial elastic wave filter layout. Specifically, it can be understood as adding the response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter to the electromagnetic response curves corresponding to the initial elastic wave filter layout obtained by simulating the initial elastic wave filter layout.

[0091] S260, determine the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial response curve of the elastic wave filter.

[0092] S270, determine the target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

[0093] In this embodiment, a resonator algorithm model enables rapid simulation of resonators with arbitrary parameters, thereby quickly obtaining the response curve and avoiding the significant time required for accurate simulation. This facilitates rapid design of elastic wave filters. The response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter are cascaded with the electromagnetic response curve corresponding to the initial elastic wave filter layout to obtain the initial response curve of the elastic wave filter. Based on the initial response curve, the first parameter corresponding to the initial response curve is determined, thus defining the target elastic wave filter layout. This allows for the rapid generation of elastic wave filters that meet target specifications, solving the problem of slow simulation and design in existing technologies. It achieves automatic, fast, and accurate simulation design of elastic wave filters while reducing the experience requirements for designers.

[0094] Optionally, the target elastic wave filter layout is determined based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter, including:

[0095] If the difference between the first parameter and the target parameter is less than or equal to the difference threshold, then the initial elastic wave filter layout determined according to the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter will be determined as the target elastic wave filter layout.

[0096] The difference threshold is preset.

[0097] In this embodiment, if all differences between the first parameter and the target parameter are less than or equal to the difference threshold, i.e. the first parameter meets the target specification, then the initial elastic wave filter layout determined by the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter is determined as the latest elastic wave filter layout; thus, an elastic wave filter that meets the target parameters can be obtained quickly.

[0098] Optional, also includes:

[0099] If the difference between the first parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonator in the elastic wave filter are adjusted according to the first parameter and the target parameter.

[0100] Specifically, if the difference between the first parameter and the target parameter is greater than the difference threshold, it can be understood that at least one of the data in the first parameter has a difference greater than the difference threshold with the target parameter; then the initial structural parameters of the resonator in the elastic wave filter are adjusted in real time according to the first parameter and the target parameter.

[0101] The second parameter corresponding to the first response curve of the elastic wave filter is determined based on the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout.

[0102] Specifically, the first response curve can refer to the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter determined by the resonator algorithm model and the electromagnetic response curve corresponding to the initial elastic wave filter layout determined by simulation of the initial elastic wave filter layout. The first response curve of the elastic wave filter is obtained by cascading the two curves. Then, the second parameter corresponding to the first response curve is determined based on the first response curve.

[0103] If the difference between the second parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonators in the elastic wave filter are adjusted according to the second parameter and the target parameter. Based on the adjusted structural parameters of the resonators, the operation of determining the second parameter corresponding to the first response curve of the elastic wave filter according to the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout is performed until all differences between the second parameter and the target parameter are less than or equal to the difference threshold, thus obtaining the target structural parameters of each resonator in the elastic wave filter.

[0104] The target structural parameters can refer to the latest structural parameters of each resonator in the elastic wave filter.

[0105] Specifically, if the difference between the second parameter and the target parameter is greater than the difference threshold, meaning that at least one data point in the second parameter still does not meet the target specification, then the initial structural parameters of the resonators in the elastic wave filter are adjusted again based on the second parameter and the target parameter. Based on the re-adjusted structural parameters of the resonators, the process returns to performing a cascade operation on the response curves corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the initial elastic wave filter layout to obtain the first response curve of the elastic wave filter. The operation of determining the corresponding second parameter based on the first response curve of the elastic wave filter is repeated until it is determined that the difference between all data points in the second parameter and the target parameter is less than or equal to the difference threshold. Then, the adjusted structural parameters of the resonators in the elastic wave filter corresponding to the second parameter are determined as the target structural parameters.

[0106] The first elastic wave filter layout and the corresponding electromagnetic response curve of the first elastic wave filter layout are determined based on the initial elastic wave filter topology and the target structural parameters of each resonator in the elastic wave filter.

[0107] Specifically, the layout of the first elastic wave filter can be determined based on the initial elastic wave filter topology and the latest structural parameters of each resonator in the elastic wave filter. The electromagnetic response curve corresponding to the first elastic wave filter layout can be determined by simulating the first elastic wave filter layout.

[0108] The third parameter corresponding to the second response curve of the elastic wave filter is determined based on the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout.

[0109] Specifically, the second response curve of the elastic wave filter is obtained by cascading the response curves corresponding to the latest structural parameters of each resonator in the elastic wave filter determined by the resonator algorithm model and the corresponding electromagnetic response curves determined by the simulation of the first elastic wave filter layout. Then, the third parameter corresponding to the second response curve of the elastic wave filter is determined based on the second response curve of the elastic wave filter.

[0110] If the difference between the third parameter and the target parameter is less than or equal to the difference threshold, then the first elastic wave filter layout is determined as the target elastic wave filter layout.

[0111] Specifically, if the difference between the third parameter and the target parameter is less than or equal to the difference threshold, that is, the third parameter meets the target specification, then the first elastic wave filter layout is determined as the latest elastic wave filter layout.

[0112] In this embodiment, if the difference between the first parameter and the target parameter is greater than a difference threshold (i.e., the difference between at least one data point in the first parameter and the target parameter is greater than the difference threshold), the initial structural parameters of the resonators in the elastic wave filter are adjusted. Based on the response curves corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the initial elastic wave filter layout, the second parameter corresponding to the first response curve of the elastic wave filter that ultimately meets the target specifications is determined. The target structural parameters of each resonator in the elastic wave filter are then determined. Next, a cascaded operation is performed based on the response curves corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the first elastic wave filter layout to determine whether the third parameter corresponding to the second response curve of the elastic wave filter meets the target specifications. If it does, the first elastic wave filter layout obtained based on the initial elastic wave filter topology and the latest structural parameters of each resonator in the elastic wave filter is determined as the target elastic wave filter layout. This enables the rapid and accurate acquisition of an elastic wave filter that meets the target specifications.

[0113] Optional, also includes:

[0114] If the difference between the third parameter and the target parameter is greater than the difference threshold, the initial elastic wave filter topology is adjusted according to the third parameter and the target parameter.

[0115] Specifically, if the difference between the third parameter and the target parameter is greater than the difference threshold, that is, the third parameter does not meet the target specification, the initial elastic wave filter topology is adjusted according to the third parameter and the target parameter.

[0116] Based on the adjusted elastic wave filter topology, the operation of determining the first elastic wave filter layout and the corresponding electromagnetic response curve of the first elastic wave filter layout according to the target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology is performed. The operation of determining the third parameter corresponding to the second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout is performed until the difference between the third parameter and the target parameter is less than or equal to the difference threshold, thus obtaining the target elastic wave filter topology.

[0117] The target elastic wave filter topology can refer to the latest elastic wave filter topology.

[0118] Specifically, based on the adjusted elastic wave filter topology, the process returns to determine the first elastic wave filter layout according to the target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology; by simulating the first elastic wave filter layout, the electromagnetic response curve corresponding to the first elastic wave filter layout is determined; a cascade operation is performed on the response curves corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the first elastic wave filter layout to obtain the second response curve of the elastic wave filter; then, the operation of determining the third parameter corresponding to the second response curve is repeated until the difference between the third parameter and the target parameter is less than or equal to the difference threshold, that is, the third parameter meets the target specification; then, the adjusted latest elastic wave filter topology corresponding to the third parameter that meets the target specification is determined as the target elastic wave filter topology.

[0119] The layout of the target elastic wave filter is determined based on the target elastic wave filter topology and the target structural parameters of the resonators in the elastic wave filter.

[0120] Specifically, the latest elastic wave filter layout can be determined based on the latest elastic wave filter topology and the latest structural parameters of the resonators in the elastic wave filter.

[0121] In this embodiment, if the difference between the third parameter and the target parameter is greater than the difference threshold, i.e., the third parameter does not meet the target specifications, the initial elastic wave filter topology is adjusted according to the third parameter and the target parameter until the third parameter meets the target specifications. The latest elastic wave filter topology is determined as the target elastic wave filter topology based on the third parameter that meets the target specifications. The latest elastic wave filter layout is determined based on the latest elastic wave filter topology and the latest structural parameters of the resonators in the elastic wave filter. This allows for the rapid and accurate acquisition of an elastic wave filter that meets the target specifications, enabling automatic, rapid, and accurate simulation design of the elastic wave filter.

[0122] Optionally, the first model is trained iteratively using the first sample set, including:

[0123] Obtain a filter topology database and a filter knowledge graph;

[0124] A first sample set is generated based on the filter topology database and the filter knowledge graph. The first sample set includes: parameter samples, filter topology structures corresponding to the parameter samples, and structural parameters of each resonator in the filter corresponding to the parameter samples.

[0125] The filter topology algorithm model is obtained by iteratively training the first model using the first sample set.

[0126] The filter topology database can include the topology of resonators in filters; the filter knowledge graph can refer to filter theory, including specific resonator structural parameters; and parameter samples can refer to target parameter samples. The filter topology database can include filter data with various characteristics, such as high-isolation duplexers and low-loss duplexers. This data can be empirical summaries from actual measurements or general conclusions derived from filter principles.

[0127] Specifically, a filter topology database and a filter knowledge graph can be established. A first sample set can be generated based on these databases and the knowledge graph. This first sample set includes: target parameter samples, the corresponding filter topologies, and the structural parameters of each resonator in the filters corresponding to the target parameter samples. The algorithm model of an artificial neural network is then iteratively trained using the target parameter samples, the corresponding filter topologies, and the structural parameters of each resonator in the filters corresponding to the target parameter samples, to obtain the filter topology algorithm model.

[0128] In one embodiment, it is also necessary to construct an algorithmic model of the artificial neural network (i.e., the first model), and iteratively train the first model using a first sample set to obtain the filter topology algorithm model. For example, the artificial neural network can be constructed using the backpropagation method. First, the number of neurons in the input layer and the number of neurons in the output layer are set; the number of hidden layers and the number of neurons in the hidden layers are also set. Furthermore, the number of neurons in the hidden layers of the artificial neural network constructed using the backpropagation method has a significant impact on the model's prediction accuracy. Using too few neurons in the hidden layers will lead to underfitting; conversely, too many neurons in the hidden layers may lead to overfitting. Therefore, the following empirical formula can be used as a reference:

[0129]

[0130] Where: Nh is the optimal number of neurons in the hidden layer, Ni is the number of neurons in the input layer; No is the number of neurons in the output layer; Ns is the number of samples in the training set; α is an arbitrary variable that can be chosen, usually ranging from 2 to 10; Tanh is used as the activation function of the artificial neural network algorithm model to construct the artificial neural network. Optionally, sigmoid, ReLU, etc., can be used as activation functions.

[0131] The filter topology database and filter theory are used to generate a first sample set to train the algorithm model of the artificial neural network, resulting in a filter topology algorithm model. Specifically, the filter topology algorithm model is developed as follows: First, the input values ​​from the filter topology database are normalized and then input into the input layer of the artificial neural network. Then, Nguyen-Widrow is used for weight initialization. Next, forward propagation is activated, and the input is processed through each layer to obtain the output of each layer and the expected value of the loss function. Then, backpropagation is performed, and the error between the output layer and the expected value is calculated based on the loss function. The weights and bias terms in the neural network are then updated based on the error. Finally, the forward and backpropagation process is repeated until the loss function is less than a preset threshold or the maximum number of iterations is reached. If the preset threshold is not reached, the artificial neural network algorithm needs to be adjusted and retrained. This process continues until the loss function is less than the preset threshold, thus obtaining the filter topology algorithm model.

[0132] Furthermore, after training is completed, it is necessary to verify the accuracy of the filter topology algorithm model. Random target parameters can be used to verify the trained topology algorithm. If the given topology can achieve and meet the target specifications, the training is completed and the filter topology algorithm model is output; otherwise, retraining is performed.

[0133] In this embodiment, by pre-establishing a filter topology database, obtaining a filter knowledge graph, generating a first sample set, and iteratively training a first model using the first sample set, a filter topology algorithm model is obtained. This model can automatically generate and optimize the layout according to the target specifications. The manual operation is only clicking the corresponding button, which improves design efficiency and reduces the experience requirements for designers.

[0134] Optionally, a second model may be trained iteratively using a second sample set, including:

[0135] Obtain the database of elastic wave resonators;

[0136] A second sample set is created based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of elastic wave resonators;

[0137] The second model is trained using the second sample set to obtain the elastic wave resonator algorithm model.

[0138] Specifically, an elastic wave resonator database is constructed, which includes various resonator response curves, actual resonator test results, and resonator simulation results. A second sample set is created based on the elastic wave resonator database. This second sample set includes: structural parameter samples of at least two types of elastic wave resonators and corresponding response curves for these structural parameter samples. The structural parameter samples of the at least two types of elastic wave resonators can be either actual resonator test results or resonator simulation results.

[0139] In one embodiment, methods for simulating the response curves corresponding to structural parameter samples of an elastic wave resonator include: precise simulation: finite element method, finite element-boundary element method, spectral element method, cascaded acceleration + finite element method, cascaded acceleration + finite element-boundary element method, etc.; phenomenological methods: equivalent circuit method, coupled mode method, reflection array method, delta function method, etc. The response curves of various resonators represent the characteristic parameters of different resonators, including: the piezoelectric material of the resonator, the electrode material of the resonator, the passivation material of the resonator, and the structural parameters of the elastic wave resonator. For example, if the elastic wave resonator is a surface acoustic wave resonator, the elastic wave resonator database includes various resonator structural parameters such as different resonator metal thicknesses, different interpolation periods, different metal duty cycles, different apertures, different pseudo-finger lengths, and different OPC structures. All parameters of the resonator structure that can affect the resonator response are included. In addition, the structural parameters must cover all structural parameters required for the simulation and design of elastic wave resonators; otherwise, the trained model will not be able to obtain an algorithm model that predicts the missing structural parameters. For example, if the resonator data used for training all have a duty cycle of 0.5, then the resulting algorithm model will not be able to predict the result of a duty cycle of 0.45.

[0140] For example, the elastic wave resonator database includes various piezoelectric materials such as wafer materials with piezoelectric effects of different tangential orientations and piezoelectric bonded wafers, such as LiTaO3, LiNbO3, quartz, and piezoelectric bonded wafers; various electrode materials in the elastic wave resonator database include metals such as Al, Cu, Au, Ti, and Ag and their alloys; and various passivation materials in the elastic wave resonator database include SiO2, SiN, etc.

[0141] If the elastic wave resonator is a bulk acoustic wave resonator, the elastic wave resonator database includes various structural dimensions such as: different electrode thicknesses, different piezoelectric layers, different resonator areas, different frequency modulation layer thicknesses, different temperature compensation layer thicknesses, and different resonator shapes; various piezoelectric materials in the elastic wave resonator database include: various tangentially oriented wafer materials with piezoelectric effects and piezoelectric bonded wafers, such as LiTaO3, LiNbO3, quartz, AlN, and piezoelectric bonded wafers; various electrode materials in the elastic wave resonator database include: metals such as Al, Cu, Au, Ti, and Ag, and their alloys; and various passivation materials in the elastic wave resonator database include: SiN, etc.

[0142] In this embodiment, an algorithm model of an artificial neural network (i.e., a second model) is also constructed. The second model is iteratively trained using a second sample set to obtain the elastic wave resonator algorithm model. For example, the artificial neural network can be constructed using the backpropagation method. First, the number of neurons in the input layer and the number of neurons in the output layer are set; the number of hidden layers and the number of neurons in the hidden layers are also set. Furthermore, the number of neurons in the hidden layers of the artificial neural network constructed using the backpropagation method has a significant impact on the model's prediction accuracy. Using too few neurons in the hidden layers will lead to underfitting; conversely, too many neurons in the hidden layers may lead to overfitting. Therefore, the following empirical formula can be used as a reference:

[0143]

[0144] Where: Nh is the optimal number of neurons in the hidden layer, Ni is the number of neurons in the input layer, No is the number of neurons in the output layer, Ns is the number of samples in the training set, and α is an arbitrary variable that can be chosen, typically ranging from 2 to 10. Then, the backpropagation artificial neural network algorithm model is constructed using Tanh as the activation function; optionally, sigmoid, ReLU, etc., can be used as activation functions.

[0145] A second sample set, generated using an elastic wave resonator database, is used to train the algorithm model of the artificial neural network, resulting in the elastic wave resonator algorithm model. Specifically, firstly, the input values ​​from the elastic wave resonator database are normalized and then input into the input layer of the artificial neural network; then, Nguyen-Widrow is used for weight initialization; next, forward propagation is activated, and the input is processed through each layer to obtain the output of each layer and the expected value of the loss function; then, backpropagation is performed, and the error between the output layer and the expected value is calculated based on the loss function; then, the weights and bias terms in the neural network are updated based on the error; finally, the forward-backward propagation process is repeated until the loss function is less than a preset threshold or the maximum number of iterations is reached. If the preset threshold is not reached, the artificial neural network algorithm needs to be adjusted and retrained. This process continues until the loss function is less than the preset threshold, thus obtaining the resonator algorithm model.

[0146] Furthermore, after obtaining the resonator algorithm model through training, it is necessary to determine its accuracy. Based on the characteristics of the resonator algorithm model and the elastic wave resonator database, corresponding verification schemes are set. If the accuracy meets the requirements, training is complete; otherwise, the artificial neural network algorithm and elastic wave resonator database are adjusted, and retraining is performed. This process continues until the accuracy requirements are met, resulting in the final resonator algorithm model. It is important to note that models trained using precise simulation and measured data can predict characteristic clutter modes such as transverse modes, higher-order modes, and multi-mode coupled modes; models trained using phenomenological methods cannot predict clutter modes that phenomenological models fail to describe. Additionally, during training, precise simulation data, phenomenological simulation data, and measured data cannot be mixed.

[0147] For example, Figure 4 This is a comparison chart of the prediction results of a resonator algorithm model provided in Embodiment 2 of the present invention. Figure 4 As shown, the database for training the resonator algorithm model in the figure can be set to include: 100 measured resonator results, using LT42A piezoelectric bonding sheet as the piezoelectric material, Al as the electrode material, a resonator electrode thickness of 175 nm, SiN as the passivation layer, duty cycles of 0.45 and 0.55, periods ranging from 0.8 μm to 1.2 μm, interpolation indices from 150 to 350, 15 to 35 reflector gratings, and apertures from 40 μm to 60 μm. For example, the structural parameters of the resonator used could be: Al as the electrode material, a resonator electrode thickness of 175 nm, LT42A piezoelectric bonding sheet as the material, SiN as the passivation layer, a duty cycle of 0.5, periods ranging from 1.01 μm, apertures ranging from 50.50 μm, 251 interpolation indices, and 30 reflector gratings. Curve 301 represents the result predicted using the elastic wave resonator algorithm model. Curve 302 represents the measured results of the elastic wave resonator. For easier observation, curve 302 has been shifted upwards by 5 dB. Comparison reveals that the characteristic points are basically consistent, and it can perfectly predict various clutter patterns. The only exception is... Figure 4 In the selected area, the measured result curve 301 shows that the feature point is composed of many small clutter waves, while the result curve 302 predicted by the elastic wave resonator algorithm model only shows one large clutter wave. This is due to the feature point setting during training, but this accuracy is sufficient to meet the needs of simulation.

[0148] In this embodiment, an elastic wave resonator database is established; a second sample set is created based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of the elastic wave resonators; a second model is trained using the second sample set to obtain an elastic wave resonator algorithm model; this enables rapid simulation of elastic wave resonators with arbitrary parameters, thereby quickly obtaining the response curves of the elastic wave resonators and avoiding the large amount of time required for accurate simulation.

[0149] For example, Figure 5 Here is a detailed flowchart of an elastic wave filter generation method provided in Embodiment 2 of the present invention, as follows: Figure 5 As shown, the specific steps in generating an elastic wave filter can be divided into different modules, specifically, an algorithm module, a synthesis module, an optimization module, a layout module, and a hybrid module.

[0150] The algorithm module is divided into two parts: constructing an artificial neural network algorithm and training it using an elastic wave resonator database to obtain an elastic wave resonator algorithm model (i.e., the resonator algorithm model); and constructing an artificial neural network algorithm and training it using a filter topology database and filter theory to obtain a filter topology algorithm model. Specifically, training the artificial neural network algorithm model using the filter topology database involves two steps: training the filter topology algorithm model of the artificial neural network, and determining the accuracy of the filter topology algorithm model. Similarly, training the artificial neural network algorithm model using the elastic wave resonator database involves two steps: training the elastic wave resonator algorithm model of the artificial neural network, and determining the accuracy of the elastic wave resonator algorithm model.

[0151] The synthesis module acquires the target parameters; inputs the target parameters into the filter topology algorithm model to obtain the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter; automatically provides the initial resonator structural parameters based on pre-stored data, and also provides the initial layout and the electromagnetic response curve of the layout; it can also determine the number of resonators, and use the elastic wave resonator algorithm module to calculate the response curve of each initial resonator; and perform power simulation to obtain the response curve of the initial elastic wave filter through cascading.

[0152] The optimization module compares the parameters corresponding to the initial response curve of the filter with the target specifications (i.e., target parameters). If they do not meet the requirements, it adjusts the structural parameters of the resonator to change the filter's response curve until the target specifications are met. It then performs tolerance analysis to verify whether the target specifications are met for process deviations. If they are met, it continues.

[0153] The layout module can draw the resonator's shape based on the optimized resonator's structural parameters, and then create the filter's layout according to the design rules.

[0154] The hybrid module performs electromagnetic simulation on the obtained filter layout to obtain the electromagnetic response curve; this electromagnetic response curve is cascaded with the response curve of the optimized resonator to obtain the filter response curve. If it meets the target specifications, the filter layout is output for production; otherwise, it is optimized again.

[0155] Example 3

[0156] Figure 6 This is a schematic diagram of the structure of an elastic wave filter generation device provided in Embodiment 3 of the present invention.

[0157] like Figure 6 As shown, the device includes:

[0158] Module 310 is used to acquire target parameters;

[0159] The input module 320 is used to input the target parameters into the filter topology algorithm model to obtain the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model with a first sample set;

[0160] The first determining module 330 is used to determine the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter.

[0161] The second determining module 340 is used to determine the target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

[0162] Optionally, the first determining module 330 includes:

[0163] The first determining unit is used to determine the initial elastic wave filter layout and the electromagnetic response curve corresponding to the initial elastic wave filter layout based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter.

[0164] The input unit is used to sequentially input the initial structural parameters of each resonator in the elastic wave filter into the resonator algorithm model to obtain the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter. The resonator algorithm model is obtained by iteratively training a second model using a second sample set.

[0165] A cascade unit is used to cascade the response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the initial elastic wave filter layout to obtain the initial response curve of the elastic wave filter.

[0166] The second determining unit is used to determine the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial response curve of the elastic wave filter.

[0167] Optionally, the second determining module 340 is specifically used for:

[0168] If the difference between the first parameter and the target parameter is less than or equal to the difference threshold, then the initial elastic wave filter layout determined according to the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter will be determined as the target elastic wave filter layout.

[0169] Optionally, the second determining module 340 is further used for:

[0170] If the difference between the first parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonator in the elastic wave filter are adjusted according to the first parameter and the target parameter.

[0171] The second parameter corresponding to the first response curve of the elastic wave filter is determined based on the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout.

[0172] If the difference between the second parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonators in the elastic wave filter are adjusted according to the second parameter and the target parameter. Based on the adjusted structural parameters of the resonators, the operation of determining the second parameter corresponding to the first response curve of the elastic wave filter according to the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout is performed until the difference between the second parameter and the target parameter is less than or equal to the difference threshold, thus obtaining the target structural parameters of each resonator in the elastic wave filter.

[0173] The first elastic wave filter layout and the corresponding electromagnetic response curve of the first elastic wave filter layout are determined based on the initial elastic wave filter topology and the target structural parameters of each resonator in the elastic wave filter.

[0174] The third parameter corresponding to the second response curve of the elastic wave filter is determined based on the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout.

[0175] If the difference between the third parameter and the target parameter is less than or equal to the difference threshold, then the first elastic wave filter layout is determined as the target elastic wave filter layout.

[0176] Optionally, the second determining module 340 is further used for:

[0177] If the difference between the third parameter and the target parameter is greater than the difference threshold, the initial elastic wave filter topology is adjusted according to the third parameter and the target parameter.

[0178] Based on the adjusted elastic wave filter topology, the operation of determining the first elastic wave filter layout and the corresponding electromagnetic response curve of the first elastic wave filter layout according to the target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology is performed. The operation of determining the third parameter corresponding to the second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout is performed until the difference between the third parameter and the target parameter is less than or equal to the difference threshold, thus obtaining the target elastic wave filter topology.

[0179] The layout of the target elastic wave filter is determined based on the target elastic wave filter topology and the target structural parameters of the resonators in the elastic wave filter.

[0180] Optional, input module 320, specifically used for:

[0181] Obtain a filter topology database and a filter knowledge graph;

[0182] A first sample set is generated based on the filter topology database and the filter knowledge graph. The first sample set includes: parameter samples, filter topology structures corresponding to the parameter samples, and structural parameters of each resonator in the filter corresponding to the parameter samples.

[0183] The filter topology algorithm model is obtained by iteratively training the first model using the first sample set.

[0184] Optional, input unit, specifically used for:

[0185] Obtain the database of elastic wave resonators;

[0186] A second sample set is created based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of elastic wave resonators;

[0187] The second model is trained using the second sample set to obtain the elastic wave resonator algorithm model.

[0188] Optionally, the target parameters include: insertion loss, out-of-band rejection, center frequency, input VSWR, output VSWR, input impedance, and output impedance.

[0189] The elastic wave filter generation device provided in the embodiments of the present invention can execute the elastic wave filter generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0190] Example 4

[0191] Figure 7 A schematic diagram of an electronic device that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0192] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0193] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0194] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as elastic wave filter generation methods.

[0195] In some embodiments, the elastic wave filter generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the elastic wave filter generation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the elastic wave filter generation method by any other suitable means (e.g., by means of firmware).

[0196] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0197] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0198] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0199] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0200] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0201] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0202] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0203] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating an elastic wave filter, characterized in that, include: Obtain the target parameters; The target parameters are input into the filter topology algorithm model to obtain the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. The filter topology algorithm model is obtained by iteratively training a first model using a first sample set. The first parameter corresponding to the initial response curve of the elastic wave filter is determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. Wherein, the first parameter is a parameter corresponding to the target parameter, including insertion loss, out-of-band rejection, center frequency, VSWR and impedance; The first parameter corresponding to the initial response curve of the elastic wave filter is determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, including: The initial elastic wave filter layout and the corresponding electromagnetic response curve are determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. The initial structural parameters of each resonator in the elastic wave filter are sequentially input into the resonator algorithm model to obtain the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter. The resonator algorithm model is obtained by iteratively training a second model using a second sample set. The initial response curve of the elastic wave filter is obtained by cascading the response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the initial elastic wave filter layout. The first parameter corresponding to the initial response curve of the elastic wave filter is determined based on the initial response curve of the elastic wave filter. The target elastic wave filter layout is determined based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

2. The method according to claim 1, characterized in that, The target elastic wave filter layout is determined based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter, including: If the difference between the first parameter and the target parameter is less than or equal to the difference threshold, then the initial elastic wave filter layout determined according to the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter will be determined as the target elastic wave filter layout.

3. The method according to claim 2, characterized in that, Also includes: If the difference between the first parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonator in the elastic wave filter are adjusted according to the first parameter and the target parameter. The second parameter corresponding to the first response curve of the elastic wave filter is determined based on the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout. If the difference between the second parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonators in the elastic wave filter are adjusted according to the second parameter and the target parameter. Based on the adjusted structural parameters of the resonators, the operation of determining the second parameter corresponding to the first response curve of the elastic wave filter according to the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout is performed until the difference between the second parameter and the target parameter is less than or equal to the difference threshold, thus obtaining the target structural parameters of each resonator in the elastic wave filter. The first elastic wave filter layout and the corresponding electromagnetic response curve of the first elastic wave filter layout are determined based on the initial elastic wave filter topology and the target structural parameters of each resonator in the elastic wave filter. The third parameter corresponding to the second response curve of the elastic wave filter is determined based on the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout. If the difference between the third parameter and the target parameter is less than or equal to the difference threshold, then the first elastic wave filter layout is determined as the target elastic wave filter layout.

4. The method according to claim 3, characterized in that, Also includes: If the difference between the third parameter and the target parameter is greater than the difference threshold, the initial elastic wave filter topology is adjusted according to the third parameter and the target parameter. Based on the adjusted elastic wave filter topology, the operation of determining the first elastic wave filter layout and the corresponding electromagnetic response curve of the first elastic wave filter layout according to the target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology is performed. The operation of determining the third parameter corresponding to the second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout is performed until the difference between the third parameter and the target parameter is less than or equal to the difference threshold, thus obtaining the target elastic wave filter topology. The layout of the target elastic wave filter is determined based on the target elastic wave filter topology and the target structural parameters of the resonators in the elastic wave filter.

5. The method according to claim 1, characterized in that, The first model is trained iteratively using the first sample set, including: Obtain a filter topology database and a filter knowledge graph; A first sample set is generated based on the filter topology database and the filter knowledge graph. The first sample set includes: parameter samples, filter topology structures corresponding to the parameter samples, and structural parameters of each resonator in the filter corresponding to the parameter samples. The filter topology algorithm model is obtained by iteratively training the first model using the first sample set.

6. The method according to claim 1, characterized in that, The second model is trained iteratively using the second sample set, including: Obtain the elastic wave resonator database; A second sample set is created based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of elastic wave resonators; The second model is trained using the second sample set to obtain the elastic wave resonator algorithm model.

7. The method according to claim 1, characterized in that, The target parameters include: insertion loss, out-of-band rejection, center frequency, input VSWR, output VSWR, input impedance, and output impedance.

8. An elastic wave filter generating device, characterized in that, include: The acquisition module is used to acquire target parameters; The input module is used to input the target parameters into the filter topology algorithm model to obtain the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model with a first sample set; The first determining module is used to determine the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. Wherein, the first parameter is a parameter corresponding to the target parameter, including insertion loss, out-of-band rejection, center frequency, VSWR and impedance; The first determining module includes: The first determining unit is used to determine the initial elastic wave filter layout and the electromagnetic response curve corresponding to the initial elastic wave filter layout based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. The input unit is used to sequentially input the initial structural parameters of each resonator in the elastic wave filter into the resonator algorithm model to obtain the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter. The resonator algorithm model is obtained by iteratively training a second model using a second sample set. A cascade unit is used to cascade the response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter and the electromagnetic response curves corresponding to the initial elastic wave filter layout to obtain the initial response curve of the elastic wave filter. The second determining unit is used to determine the first parameter corresponding to the initial response curve of the elastic wave filter based on the initial response curve of the elastic wave filter. The second determining module is used to determine the target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the elastic wave filter generation method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the elastic wave filter generation method according to any one of claims 1-7.

Images